Artificial intelligence has simplified the treatment of diseases: it has solved a problem that scientists have not been given for 50 years
The researchers believe that artificial intelligence was able to solve a scientific problem that is already 50 years old. This can lead to dramatic changes in the fight against disease. What is this problem and why is it so important for humanity, the publication told Independent.
For years, scientists have wrestled with the problem of protein folding - mapping the three-dimensional shapes of proteins responsible for diseases from cancer to COVID-19.
Google's Deepmind claims to have created an artificial intelligence program called AlphaFold that can solve these problems in a matter of days.
If it works, experts say the solution came “decades” earlier than expected and could have a transformative effect on how diseases are treated.
There are currently 200 million proteins known, but only a fraction of them have actually been researched with full understanding of what they do and how they work. Even those that have been successfully studied often rely on expensive and time-consuming methods, with scientists spending years deploying each structure and relying on equipment that can cost millions of dollars.
DeepMind has been working on the AI Critical Evaluation of Protein Structure Prediction (CASP14) project with a group of scientists who have been working on the subject since 1994.
On the subject:
"Proteins are extremely complex molecules, and their precise three-dimensional structure is key to many of the functions they perform, such as insulin, which regulates our blood sugar levels, and antibodies that help us fight infections," said Dr. John Moult. “Even tiny rearrangements in these vital molecules can have catastrophic consequences for our health, so one of the most effective ways to understand disease and find new treatments is to study the proteins involved.”
“There are tens of thousands of human proteins and many billions of other species, including bacteria and viruses, but determining the shape of just one requires expensive equipment and can take years,” he added.
In a recent test, DeepMind reported that AlphaFold determined the shape of about two-thirds of the proteins with an accuracy comparable to laboratory experiments. The results of these tests have been published online for other scientists to study.
Now the researchers behind the project say there is still a lot to be done, including figuring out how several proteins form complexes and how they interact with DNA.
DeepMind plans to submit a document detailing its system to a peer-reviewed journal for study by the wider scientific community.
You may be interested in: top New York news, stories of our immigrants and helpful tips about life in the Big Apple - read it all on ForumDaily New York.
Professor Venki Ramakrishnan, Nobel laureate and President of the Royal Society, said: “This computational work represents a staggering step forward in solving the problem of protein folding, a daunting task in biology 50 years ago. This happened decades earlier than many experts in the field predicted. It will be interesting to see how this revolutionizes biological research. ”
DeepMind noted that, among other things, predicting protein structures could be an important part of the response to future pandemics, and that the company has already used its machine learning technology to study the protein structures of the SARS-CoV-2 virus that causes COVID-19.
Read also on ForumDaily:
stdClass Object ([term_id] => 928 [name] => scientists [taxonomy] => post_tag [slug] => uchenye)scientists
stdClass Object ([term_id] => 13189 [name] => artificial intelligence [taxonomy] => post_tag [slug] => iskusstvennyj-intellekt)Artificial Intelligence
stdClass Object ([term_id] => 27233 [name] => World [taxonomy] => category [slug] => mir)World
Do you want more important and interesting news about life in the USA and immigration to America? Subscribe to our page in Facebook. Choose the "Display Priority" option and read us first. And don't forget to subscribe to ForumDaily Woman and ForumDaily New York - there you will find a lot of interesting and positive information.